Abstract

The cold start problem has always been a major challenge for recommender systems. It arises when the system lacks rating records for new users or items. Addressing the challenge of providing personalized recommendations in the cold start scenario is crucial. This research proposes a new hybrid recommender system named CoDFi-DL which combines demographic and enhanced collaborative filtering. The demographic filtering is performed through a deep neural network (DNN) and used to solve the new user cold start problem. The enhanced collaborative filtering component of our model focuses on delivering personalized recommendations through a neighborhood-based method. The major contribution in this research is the DNN-based demographic filtering which overcomes the new user cold start problem and enhances the collaborative filtering process. Our system significantly improves the relevancy of the recommendation task and thus provides personalized recommended items to cold users. To evaluate the effectiveness of our approach, we conducted experiments on real multi-label datasets, 1M and 100K MovieLens. CoDFi-DL recommender system showed higher performance in comparison with baseline methods, achieving lower RMSE rates of 0.5710 on the 1M MovieLens dataset and 0.6127 on the 100K MovieLens dataset.

Abstract

The rapid expansion of contextual information from smartphones and Internet of Things (IoT) devices paved the way for Context-Aware Recommendation Systems (CARS). This abundance of contextual data heralds a transformative era for traditional recommendation systems. In alignment with this trend, we propose a novel model which provides personalized recommendations based on context. Our approach uses K-means algorithm to cluster users based on contextual features. Then, the model performs collaborative filtering based on matrix factorization with enhanced contextual biases to provide relevant recommendations. We demonstrated the performance of our method through experiments conducted on the movie recommender dataset LDOS-CoMoDa. The experimental results showed the effective performance of our proposal compared to reference methods, achieving an RMSE of 0.7416 and an MAE of 0.6183.

Abstract

The integration of social networking concepts into the IoT environment has led to the Social Internet of Things
(SIoT) paradigm which enables connected devices and people to facilitate information sharing, interact, and
enable a variety of attractive applications. However, with this emerging paradigm, people feel cautious and
wary. They worry about violating their privacy and revealing their data. Without trustworthy mechanisms to
guarantee the reliability of user’s communications and interactions, the SIoT will not reach enough popularity
to be considered as a cutting-edge technology. Accordingly, trust management becomes a major challenge
to improve security and provide qualified services. Therefore, we overcome these issues through proposing
an adaptive trust management model based on Adaptive Neuro-Fuzzy Inference System (ANFIS) in order to
estimate the trust level of objects in the Social Internet of Things. We formalized and implemented a new trust
management model built ANFIS, to analyze different trust parameters, estimate the trust level of objects and
distinguish malicious behavior from benign behaviors. Experimentation made on a real data set proves the
performance and the resilience of our trust management model.

Abstract

The pharmaceutical industry is facing challenges due to various factors such as supply chain disruptions, changing consumer behavior, and regulatory changes. Accurate demand forecasting is essential to ensure an adequate supply of drugs. The goal of this work is to forecast paracetamol product demand. For this purpose, we propose a hybrid forecasting model combining two effective forecasting techniques: SARIMA (Seasonal AutoRegressive Integrated Moving Average) and ANFIS (Adaptive Neuro-Fuzzy Inference System). This proposal consists of nonlinear components of time series by ANFIS and adjusting the result by the mean of the residuals of the SARIMA to improve the accuracy and performance of ANFIS predictions. Before the prediction phase, we preprocess our data and detect the anomalies in our dataset with Locally Selective Combination in Parallel Outlier Ensembles (LSCP). Then, by treating these anomalies as missing values, they are imputed using the combination of Fuzzy-Possibilistic c-means (FCM) with support vector regression (SVR) and a genetic algorithm (GA). Finally, we evaluate the performance of the model and some known models based on MAPE. We choose the hybrid model SARIMA-ANFIS that provides the most accurate and reliable forecasting.

Abstract

Sleep is a vital process for human well-being. Sleep scoring is performed by experts using polysomnograms, that record several body activities, such as electroencephalograms (EEG), electrooculograms (EOG), and electromyograms (EMG). This task is known to be exhausting, biased, time-consuming, and prone to errors. Current automatic sleep scoring approaches are mostly based on single-channel EEG and do not produce explainable results. Therefore, we propose a heterogeneous ensemble learning-based approach where we combine accuracy-based learning classifier systems with different algorithms to produce a robust, explainable, and enhanced classifier. The efficiency of our approach was evaluated using the Sleep-EDF benchmark dataset. The proposed models have reached an accuracy of 89.2% for the stacking model and 87.9% for the voting model, on a multi-class classification task based on the R&K guidelines.

Abstract

Supervised machine learning techniques include classification and regression. In regression, the objective is to map a real-valued output to a set of input features. The main challenge that existing methods for regression encounter is how to maintain an accuracy-simplicity balance. Since Regression Trees (RTs) are simple to interpret, many existing works have focused on proposing RT and Model Tree (MT) induction algorithms. MTs are RTs with a linear function at the leaf nodes rather than a numerical value are able to describe the relationship between the inputs and the output. Traditional RT induction algorithms are based on a top-down strategy which often leads to a local optimal solution. Other global approaches based on Evolutionary Algorithms (EAs) have been proposed to induce RTs but they can require an important calculation time which may affect the convergence of the algorithm to the solution. In this paper, we introduce a novel approach called Bi-level Evolutionary Model Tree Induction algorithm for regression, that we call BEMTI, and which is able to induce an MT in a bi-level design using an EA. The upper-level evolves a set of MTs using genetic operators while the lower-level optimizes the Linear Models (LMs) at the leaf nodes of each MT in order to fairly and precisely compute their fitness and obtain the optimal MT. The experimental study confirms the outperformance of our BEMTI compared to six existing tree induction algorithms on nineteen datasets.

Abstract

Since several decade, the Internet of Things IoT hasattracted enormous interest in the research communityand industry. However, IoT technologies has completelytransformed vehicular ad hoc networks (VANETs) intothe « Internet of Vehicles » IoV. In IoV networks, we needto integrate many different technologies, services andstandards. However, the heterogeneity and large numberof vehicles will increase the need of data security.The IoV security issues are critical because of the vulnerabilitiesthat exist during the transmission of informationthat expose the IoV to attacks. Each attack hasa security procedure. Many protocols and mechanismsexist to combat or avoid this communication securityproblem. One of these protocols is VIPER (a Vehicleto-Infrastructure communication Privacy EnforcementpRotocol). In our work, we try to improve this protocolby using Blockchain technology and certificationauthority.

Abstract

This paper introduces TradeStrat-ML, a novel framework for stock market trading. It integrates various techniques: technical analysis, hybrid machine learning models, multi-agent-based simulations (MABS), and financial modeling for stock market analysis and future predictions. The process involves using a Convolutional Neural Network (CNN) to extract features from preprocessed financial data. The output of this model is then combined with three machine learning models (Gated Recurrent Unit (GRU), Extreme Gradient Boosting (XGBoost), and Support Vector Regression (SVR)) to predict future stock price indices. Subsequently, the models are evaluated, compared, and the most accurate model is selected for stock market prediction. In the final stage, the selected model, along with the Simple Moving Average (SMA) indicator, is used to develop an optimized trading strategy. The TradeStrat-ML system is organized into four main layers and validated using MABS simulations. Comparative analysis and simulation experiments collectively indicate that this new combination prediction model is a potent and practical tool for informed investment decision-making.

Abstract